by msaleme · MCP Server · ★ 20
Agent Security Harness Even if an agent is properly authenticated and authorized, can it still be manipulated into unsafe or policy-violating behavior? 474 executable security tests across 33 modules. MCP + A2A + L402 + x402 wire-protocol testing. Decision-layer attack scenarios. One away. $ agent-security test mcp --url http://localhost:8080/mcp Running MCP Protocol Security Tests v4.2... MCP-001: Tool List Integrity Check [PASS] (0.234s) MCP-002: Tool Registration via Call Injection [PASS] (0.412s) MCP-003: Capability Escalation via Initialize [FAIL] (0.156s) ... Results: 8/10 passe
| Stars | 20 |
| Forks | 5 |
| Language | Python |
| Category | MCP Server |
| License | Apache-2.0 |
| Quality Score | 71.2180798021588/100 |
| Open Issues | 9 |
| Last Updated | 2026-07-05 |
| Created | 2025-11-15 |
| Platforms | mcp, python |
| Est. Tokens | ~15k |
Explore other popular mcp server tools:
red-team-blue-team-agent-fabric is 470 security tests for AI agent systems — MCP, A2A, x402/L402, decision governance, benchmark integrity, skill supply chain. AIUC-1 pre-cert, NIST AI 800-2 aligned, CVE-2026-25253 reproduction. v4.4.2. It is categorized as a MCP Server with 20 GitHub stars.
red-team-blue-team-agent-fabric is primarily written in Python. It covers topics such as a2a-protocol, agent-security, agentic-ai.
You can find installation instructions and usage details in the red-team-blue-team-agent-fabric GitHub repository at github.com/msaleme/red-team-blue-team-agent-fabric. The project has 20 stars and 5 forks, indicating an active community.
red-team-blue-team-agent-fabric is released under the Apache-2.0 license, making it free to use and modify according to the license terms.